人工智能辅助自我诊断中的医学错误信息:开发一种分析大型语言模型的方法 (EvalPrompt)
Troy Zada1, Natalie Tam1, Francois Barnard1
1Department of Management Sciences and Engineering, University of Waterloo, 200 University Avenue West, Waterloo, ON, N2L 3G1, Canada, 1 5198884567 ext 33279.
JMIR formative research
|March 10, 2025
概括
像ChatGPT这样的大型语言模型 (LLM) 显示出适度的自我诊断能力,准确度低于通过值. 仅仅依靠LLM来获取医疗信息,就有可能因不清楚和不准确的答案导致错误的信息.
科学领域:
- 医疗保健中的人工智能
- 医疗信息学 医疗信息学
- 自然语言处理自然语言处理.
背景情况:
- 大型语言模型 (LLM) 正在迅速融入医疗保健,促使人们讨论它们提高质量和可访问性的潜力.
- 虽然LLM可以通过医学考试,但它们用于自我诊断和传播错误信息的可能性需要评估.
研究的目的:
- 评估LLMs的有效性,特别是ChatGPT,用于个人自我诊断.
- 在模拟的自我诊断场景中评估LLM响应的清晰度,正确性和稳定性.
主要方法:
- 使用医学执照考试问题开发了EvalPrompt方法.
- 实验1:提示聊天GPT与模拟自我诊断的开放式问题.
- 实验2:通过使用句子中断来评估强度,以模仿缺失的信息.
主要成果:
- 在实验1中,ChatGPT-4.0的答案仅对31%的问题被认为是正确的.
- 在实验2中,61%的答案仍然是正确的,这表明了强度,但也可能导致错误信息.
- 聊天GPT-4.0的清晰度和正确性低于60%的合格值.
结论:
- 目前,LLM的自我诊断能力有限,答案往往不清楚和不准确.
- 建议在使用LLM产生的医疗建议时谨慎使用,因为存在重大错误信息风险.
- 需要开发一个全面的自我诊断数据集,以提高医疗保健中的LLM可靠性.
相关概念视频
Issues And Trends In Healthcare Delivery System
5.5K
The issues and trends in healthcare delivery are constantly changing. The COVID-19 pandemic is one recent issue that wreaked havoc on healthcare systems, causing a shortage of healthcare workers, high demand for medicines and supplies, and increased medical expenditure due to a lack of insurance. Other issues include rising healthcare costs and care fragmentation.
Cost Containment
Payment for healthcare services has historically promoted adoption of costly and often unnecessary or inefficient...
Cost Containment
Payment for healthcare services has historically promoted adoption of costly and often unnecessary or inefficient...
5.5K
Documentation of Nursing Diagnosis
1.2K
The nurse documents nursing diagnoses and enters them into the patient record. The identified patient's nursing diagnosis is either written out with a plan of care or entered into the electronic health record.
In some settings, data-driven computerized decision support systems are in place, allowing for more accurate nursing diagnoses. The database within one of these systems includes diagnostic labels defining characteristics, activities, and indicators for nursing. A nurse enters...
In some settings, data-driven computerized decision support systems are in place, allowing for more accurate nursing diagnoses. The database within one of these systems includes diagnostic labels defining characteristics, activities, and indicators for nursing. A nurse enters...
1.2K
MALDI-TOF Mass Spectrometry
4.7K
Mass spectrometry is a powerful characterization technique that can identify and separate a wide variety of compounds ranging from chemical to biological entities, based on their mass-to-charge ratio (m/z). The instruments that allow this detection, known as mass spectrometers, have three components: an ion source, a mass analyzer, and a detector. These spectrometers differ based on the nature of their ion source and analyzers.
Matrix-assisted laser desorption ionization (MALDI) is a commonly...
Matrix-assisted laser desorption ionization (MALDI) is a commonly...
4.7K
Enzyme-Linked Immunosorbent Assay
12.3K
In 1971, Peter Perlman and Eva Engvall developed an Enzyme-linked immunosorbent assay (ELISA or EIA). ELISA differs from western blot in that the assays are conducted in microtiter plates or in vivo rather than on an absorbent membrane.
There are many different types of ELISAs, but they all involve an antibody molecule whose constant region binds an enzyme, leaving the variable region free to bind its specific antigen. Enzyme-substrate reaction allows the antigen to be visualized or...
There are many different types of ELISAs, but they all involve an antibody molecule whose constant region binds an enzyme, leaving the variable region free to bind its specific antigen. Enzyme-substrate reaction allows the antigen to be visualized or...
12.3K


